NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
172 results for “keyword:"sparse autoencoders"” in ICLR 2027. 33 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DeCoS: Decoding by Contrasting Steered Features Reduces Hallucinations in Large Language Models▼4.5k2.67
[PDF]From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features▲9.2k2.67
[PDF]PUSH: Sparse Representation Dynamics Enable Cost-Efficient Reinforcement Learning in LLMs▼1.2k3.00
[PDF]Training Selects Among Behaviorally Equivalent Computations in In-Context Dictionary Learning▲5.4k3.00
[PDF]Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space▲3952.67
[PDF]PersJEPA: Interpretable Language Model Personalization through Sparse Residual Prediction▼1.2k1.67
[PDF]SPAR: SPARSE PHASE-AWARE ADAPTATION OF REPRESENTATIONS FOR TIME SERIES FORECASTING WITH EXOGENOUS VARIABLES▲1.7k3.33
[PDF]BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain▲5.4k3.00
[PDF]Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations▼4.5k2.67
[PDF]From Representation to Behavioral Control: An Empirical Study of Fine-Grained and Unified Emotional Signals in LLMs▼4.3k2.00
[PDF]Split, Not Sparse: Ground-Truth Feature Superposition Across Scientific Domains and Model Scale▼1361.33
[PDF]Why This Expert? A Feature-Level Analysis of Routing in Mixture-of-Experts with Sparse Autoencoders▼1.2k1.67
[PDF]RefusalTrace: Localizing and Validating the Internal Refusal Pathway of LLMs with Sparse Autoencoder Features▲9.7k2.75
[PDF]Evaluating Semantic State Response and Generated Visual Feedback under Distinct Input Contracts▼1361.33
[PDF]When Weak Features Hide: Separating Statistical Detection from Sparse Autoencoder Recovery▲6.1k2.00
[PDF]Interpreting Sparse Autoencoder Features in Cytometry Foundation Models through In Silico Perturbations▼4.3k2.00
[PDF]Faithful Rules Are Not Enough: Boolean Surrogates for Deep RL and an Audit of Their Concepts▼4.5k2.67
[PDF]The Model Already Has a Dictionary: Cumulative SVD Features as a Training-Free Alternative to Sparse Autoencoders▲3952.67
[PDF]Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders▼4.3k2.00
[PDF]SAIL: Sparse Autoencoders for Interpretable Alignment of Human Vision and Multimodal Large Language Models▲9.2k2.67
[PDF]Don't Ignore Them: Scaffold Features Matter for Stable SAE Steering in Diffusion Models▲3952.67
[PDF]What Goes Up Should Come Down: A Training-Distribution Control for Interpretability Metrics▲5103.00
[PDF]Distributed Geographic Identity Encoding in Vision-Language Models: From Linear Probing to Sparse Autoencoder Feature Ablation, and Why Post-Hoc Debiasing Fails▲11.00
[PDF]What Do Benchmarks Measure? Discovering Benchmark Demands and Grounding System Capabilities▲20k2.67
[PDF]SAE Interventions Can Be Unreliable: Post-Intervention Recovery of Suppressed Behavior▼4.3k2.00
Withdrawn or desk rejected (33)
[PDF]SN-ABSTOPK: AN UNROLLED SPATIAL-NORMATIVE SPARSE AUTOENCODER FOR MEDICAL FOUNDATION MODELSWithdrawn1.00